It is typical to use individual observations instead of rational subgroups when there is no basis for forming subgroups, when there is a long interval between observations becoming available, when testing is destructive or expensive, or for many other reasons. Other charts such as the exponentially weighted moving average and cumulative sum may be more appropriate to detect smaller shifts more quickly.
Each point on the chart represents the value of an individual observation.
The center line is the process mean. If unspecified, the process mean is the mean of the individual observations.
The control limits are either:
If unspecified, the process sigma is the standard deviation of the individual observations, unless the chart is combined with an MR-chart where it is estimated as described for the respective chart. For an in-control process, both estimators are unbiased, and the standard deviation is a more efficient estimator. For a process with special causes of variation, both estimators are biased, and it may be preferable to use the median moving range estimator.
The observations are assumed to be independent and normally distributed. If the process shows a moderate departure from normality, it may be preferable to transform the variable so that it is approximately normally distributed.
It is important to ensure process variability is in a state of statistical control before using the I-chart to investigate if the process mean is in control. Therefore an I-chart is often combined with an MR-chart to monitor process variability, although some authors question the benefit of an additional MR-chart.
From the Statistical Reference Guide for Analyse-it 6.24.0: https://analyse-it.com/docs/user-guide/process-control/i
We use essential cookies to run the site. With your permission we'd also like to use analytics and
advertising cookies to see how visitors find and use Analyse-it, so we can keep improving it and reach
more people like you.
You can change your mind at any time, see our
Privacy policy.